© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71924
    Prev
    Next
    INDEX
    Explanations

    Murray and similar names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    และ
    -3.38
    }
    -2.97
    纐
    -2.83
     یا
    -2.81
     และ
    -2.78
     หรือ
    -2.73
     или
    -2.67
    ꪻ
    -2.66
    🫃
    -2.63
    たまに
    -2.59
    POSITIVE LOGITS
     After
    3.73
     When
    3.50
    are
    2.81
    to
    2.63
     For
    2.59
     sämtliche
    2.59
     During
    2.58
    )
    2.52
    k
    2.48
    瑒
    2.41
    Activations Density 0.003%

    No Known Activations